# Footwear Size Recommendation System

arXiv: https://arxiv.org/abs/1806.11423 · HTML: https://mlsanity.com/paper/1806.11423/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2018.

## Built on by (most cited first, 10 of 10)

- [PreSizE: Predicting Size in E-Commerce using Transformers](https://mlsanity.com/paper/2105.01564/) (2021)
- [Unsupervised Extractive Summarization of Emotion Triggers](https://mlsanity.com/paper/2306.01444/) (2023)
- [Classification for everyone : Building geography agnostic models for fairer recognition](https://mlsanity.com/paper/2312.02957/) (2023)
- [Shaping Political Discourse using multi-source News Summarization](https://mlsanity.com/paper/2312.11703/) (2023)
- [Exploring Graph Based Approaches for Author Name Disambiguation](https://mlsanity.com/paper/2312.08388/) (2023)
- [Sarcasm Detection in a Disaster Context](https://mlsanity.com/paper/2308.08156/) (2023)
- [Zero-shot Active Learning Using Self Supervised Learning](https://mlsanity.com/paper/2401.01690/) (2024)
- [Detecting anxiety from short clips of free-form speech](https://mlsanity.com/paper/2312.15272/) (2023)
- [Exploring intra-task relations to improve meta-learning algorithms](https://mlsanity.com/paper/2312.16612/) (2023)
- [Tailor: Size Recommendations for High-End Fashion Marketplaces](https://mlsanity.com/paper/2401.01978/) (2024)

## Abstract (arXiv)

While shopping for fashion products, customers usually prefer to try-out products to examine fit, material, overall look and feel. Due to lack of try out options during online shopping, it becomes pivotal to provide customers with as much of this information as possible to enhance their shopping experience. Also it becomes essential to provide same experience for new customers. Our work here focuses on providing a production ready size recommendation system for shoes and address the challenge of providing recommendation for users with no previous purchases on the platform. In our work, we present a probabilistic approach based on user co-purchase data facilitated by generating a brand-brand relationship graph. Specifically we address two challenges that are commonly faced while implementing such solution. 1. Sparse signals for less popular or new products in the system 2. Extending the solution for new users. Further we compare and contrast this approach with our previous work and show significant improvement both in recommendation precision and coverage.